Changes between Initial Version and Version 1 of NCHCCloudCourse100802/Lab4


Ignore:
Timestamp:
Aug 6, 2010, 2:39:25 AM (14 years ago)
Author:
jazz
Comment:

--

Legend:

Unmodified
Added
Removed
Modified
  • NCHCCloudCourse100802/Lab4

    v1 v1  
     1{{{
     2#!html
     3<div style="text-align: center;"><big
     4 style="font-weight: bold;"><big><big>實做四: Hadoop 程式編譯</big></big></big></div>
     5}}}
     6[[PageOutline]]
     7
     8= 練習 1 : Word Count 初級版 =
     9
     10 * 上傳內容到hdfs內
     11
     12{{{
     13$ cd /opt/hadoop
     14$ mkdir lab4_input
     15$ echo "I like NCHC Cloud Course." > lab4_input/input1
     16$ echo "I like nchc Cloud Course, and we enjoy this course." > lab4_input/input2
     17$ bin/hadoop fs -put lab4_input lab4_input
     18$ bin/hadoop fs -ls lab4_input
     19}}}
     20
     21 * 下載 [http://secuse.nchc.org.tw/class/WordCount.java WordCount.java] 並存到/opt/hadoop;
     22{{{
     23$ wget http://secuse.nchc.org.tw/class/WordCount.java
     24}}}
     25
     26 * 運作程式
     27
     28{{{
     29$ mkdir MyJava
     30$ javac -classpath hadoop-*-core.jar -d MyJava WordCount.java
     31$ jar -cvf wordcount.jar -C MyJava .
     32$ bin/hadoop jar wordcount.jar WordCount lab4_input/ lab4_out1/
     33$ bin/hadoop fs -cat lab4_out1/part-00000
     34}}}
     35
     36 * lab4_out1 執行結果
     37{{{
     38#!text
     39Cloud   2
     40Course, 1
     41Course. 1
     42I       2
     43NCHC    1
     44and     1
     45course. 1
     46enjoy   1
     47like    2
     48nchc    1
     49this    1
     50we      1
     51}}}
     52-----
     53
     54= 練習 2 : Word Count 進階版 =
     55
     56{{{
     57$ echo "\." >pattern.txt && echo "\," >>pattern.txt
     58$ bin/hadoop fs -put pattern.txt ./
     59$ mkdir MyJava2
     60}}}
     61
     62
     63 * 下載 [raw-attachment:wiki:Hadoop_Lab4:WordCount2.java WordCount2.java] 並存到/opt/hadoop;
     64{{{
     65$ wget http://trac.nchc.org.tw/cloud/raw-attachment/wiki/Hadoop_Lab4/WordCount2.java
     66}}}
     67
     68{{{
     69$ javac -classpath hadoop-*-core.jar -d MyJava2 WordCount2.java
     70$ jar -cvf wordcount2.jar -C MyJava2 .
     71$ bin/hadoop jar wordcount2.jar WordCount2 lab4_input lab4_out2 -skip pattern.txt
     72$ bin/hadoop fs -cat lab4_out2/part-00000
     73}}}
     74
     75 * lab4_out2 執行結果
     76{{{
     77#!text
     78Cloud   2
     79Course  2
     80I       2
     81NCHC    1
     82and     1
     83course  1
     84enjoy   1
     85like    2
     86nchc    1
     87this    1
     88we      1
     89}}}
     90
     91{{{
     92$ bin/hadoop jar wordcount2.jar WordCount2 -Dwordcount.case.sensitive=false lab4_input lab4_out3 -skip pattern.txt
     93$ bin/hadoop fs -cat lab4_out3/part-00000
     94}}}
     95
     96 * lab4_out3 執行結果
     97{{{
     98#!text
     99and     1
     100cloud   2
     101course  3
     102enjoy   1
     103i       2
     104like    2
     105nchc    2
     106this    1
     107we      1
     108}}}